Neural network and antenna configuration indication

Abstract

Wireless communications systems and methods related to indicating antenna configuration information and neural network information are disclosed. Neural network information may be selected for an encoder side based on an antenna configuration of a first device housing the encoder. This information may be transmitted with the antenna configuration information to a second device, which may jointly train the neural network with the first device. The first device may further transmit one or more weights after the training, which are stored with the antenna configuration information at the second device as well. When a third device with similar antenna configuration as the first device establishes communication with the second device, the second device may transmit neural network information, as well as weights, to the third device. The third device may use this information, instead of default information, to speed up neural network initialization and training.

What is claimed is: 
     
       1. A method of wireless communication, comprising:
 establishing, by a first wireless communications device, communication with a second wireless communications device; 
 determining, by the first wireless communications device, a neural network to use for the communication with the second wireless communications device based on an antenna configuration of the first wireless communications device; and 
 transmitting, by the first wireless communications device in response to determining the neural network, antenna configuration information and at least one neural network parameter based on the neural network to the second wireless communications device. 
 
     
     
       2. The method of  claim 1 , wherein:
 the determining further comprises selecting the neural network from a plurality of neural networks, and 
 the at least one neural network parameter comprises an identifier of the selected neural network. 
 
     
     
       3. The method of  claim 1 , wherein:
 the first wireless communications device comprises a user equipment and the second wireless communications device comprises a base station, and 
 the transmitting is on a physical uplink control channel. 
 
     
     
       4. The method of  claim 1 , wherein:
 the first wireless communications device comprises a base station and the second wireless communications device comprises a user equipment, and 
 the transmitting is on a physical downlink control channel. 
 
     
     
       5. The method of  claim 1 , wherein:
 the first wireless communications device comprises a first user equipment (UE) and the second wireless communications device comprises a second UE, and 
 the transmitting is on a physical sidelink control channel. 
 
     
     
       6. The method of  claim 1 , further comprising:
 training, by the first wireless communications device, the neural network in coordination with the second wireless communications device; and 
 transmitting, by the first wireless communications device, at least one training weight resulting from the training to the second wireless communications device. 
 
     
     
       7. The method of  claim 1 , wherein the antenna configuration information comprises a panel orientation of an antenna array of the first wireless communications device, a dimension of the antenna array, and polarization information of the antenna array. 
     
     
       8. A method of wireless communications, comprising:
 establishing, by a first wireless communications device, communication with a second wireless communications device; 
 receiving, by the first wireless communications device from the second wireless communications device, antenna configuration information of an antenna configuration at the second wireless communications device and at least one neural network parameter of a neural network at the second wireless communications device for the communication in response to a determination of the neural network; and 
 storing, by the first wireless communications device, the antenna configuration information and the at least one neural network parameter. 
 
     
     
       9. The method of  claim 8 , further comprising:
 establishing, by the first wireless communications device, a second communication with a third wireless communications device. 
 
     
     
       10. The method of  claim 9 , further comprising:
 determining, by the first wireless communications device, that an antenna configuration of the third wireless communications device shares a characteristic with the antenna configuration information from the second wireless communications device; and 
 transmitting, by the first wireless communications device in response to the determining, the at least one neural network parameter to the third wireless communications device for use for the second communication. 
 
     
     
       11. The method of  claim 9 , further comprising:
 coordinating, by the first wireless communications device, with the second wireless communications device to train the neural network; and 
 receiving, by the first wireless communications device in response to the coordinating, at least one training weight for the neural network from the second wireless communications device. 
 
     
     
       12. The method of  claim 11 , further comprising:
 determining, by the first wireless communications device, that an antenna configuration of the third wireless communications device shares a characteristic with the antenna configuration at the second wireless communications device; and 
 transmitting, by the first wireless communications device in response to the determining, the at least one neural network parameter and the at least one training weight to the third wireless communications device for use for the second communication. 
 
     
     
       13. The method of  claim 11 , further comprising:
 providing, by the first wireless communications device to the second wireless communications device, an allocation of resources on which the at least one training weight is received. 
 
     
     
       14. The method of  claim 8 , wherein the neural network comprises one from among a plurality of neural networks preconfigured at the first wireless communications device and the second wireless communications device. 
     
     
       15. The method of  claim 8 , wherein the antenna configuration information comprises a panel orientation of an antenna array of the second wireless communications device, a dimension of the antenna array, and polarization information of the antenna array. 
     
     
       16. A first wireless communications device, comprising:
 a transceiver configured to establish communication with a second wireless communications device; and 
 a processor configured to determine a neural network to use for the communication with the second wireless communications device based on an antenna configuration of the first wireless communications device, 
 wherein the transceiver is further configured to transmit antenna configuration information and at least one neural network parameter based on the neural network to the second wireless communications device in response to the processor determining the neural network. 
 
     
     
       17. The first wireless communications device of  claim 16 , wherein:
 the processor is further configured, for the determination, to select the neural network from a plurality of neural networks, and 
 the at least one neural network parameter comprises an identifier of the selected neural network. 
 
     
     
       18. The first wireless communications device of  claim 16 , wherein:
 the first wireless communications device comprises a user equipment and the second wireless communications device comprises a base station, and 
 the transmission is on a physical uplink control channel. 
 
     
     
       19. The first wireless communications device of  claim 16 , wherein:
 the first wireless communications device comprises a base station and the second wireless communications device comprises a user equipment, and 
 the transmission is on a physical downlink control channel. 
 
     
     
       20. The first wireless communications device of  claim 16 , wherein:
 the first wireless communications device comprises a first user equipment (UE) and the second wireless communications device comprises a second UE, and 
 the transmission is on a physical sidelink control channel. 
 
     
     
       21. The first wireless communications device of  claim 16 , wherein:
 the processor is further configured to train the neural network in coordination with the second wireless communications device, and 
 the transceiver is further configured to transmit at least one training weight resulting from the training to the second wireless communications device. 
 
     
     
       22. The first wireless communications device of  claim 16 , wherein the processor comprises a neural network unit integrated with the transceiver. 
     
     
       23. The first wireless communications device of  claim 16 , wherein the processor comprises an application processor separate from the transceiver. 
     
     
       24. A first wireless communications device, comprising:
 a transceiver configured to:
 establish communication with a second wireless communications device; and 
 receive, from the second wireless communications device, antenna configuration information of an antenna configuration at the second wireless communications device and at least one neural network parameter of a neural network at the second wireless communications device for the communication in response to a determination of the neural network; and 
 
 a processor configured to store the antenna configuration information and the at least one neural network parameter at the first wireless communications device. 
 
     
     
       25. The first wireless communications device of  claim 24 , wherein the transceiver is further configured to:
 establish a second communication with a third wireless communications device. 
 
     
     
       26. The first wireless communications device of  claim 25 , wherein:
 the processor is further configured to determine that an antenna configuration of the third wireless communications device shares a characteristic with the antenna configuration information from the second wireless communications device; and 
 the transceiver is further configured to transmit, in response to the determination, the at least one neural network parameter to the third wireless communications device for use for the second communication. 
 
     
     
       27. The first wireless communications device of  claim 25 , wherein:
 the processor is further configured to coordinate with the second wireless communications device to train the neural network, and 
 the transceiver is further configured to receive, in response to the coordination, at least one training weight for the neural network from the second wireless communications device. 
 
     
     
       28. The first wireless communications device of  claim 27 , wherein:
 the processor is further configured to determine that an antenna configuration of the third wireless communications device shares a characteristic with the antenna configuration at the second wireless communications device; and 
 the transceiver is further configured to transmit, in response to the determination, the at least one neural network parameter and the at least one training weight to the third wireless communications device for use for the second communication. 
 
     
     
       29. The first wireless communications device of  claim 24 , wherein the processor comprises a neural network unit integrated with the transceiver. 
     
     
       30. The first wireless communications device of  claim 24 , wherein the processor comprises an application processor separate from the transceiver.